© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55593
    Prev
    Next
    INDEX
    Explanations

    phase and alignment

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to technical mentions of “phase” (and related timing/offset terms like phase-shift, phase offset) in engineering and signal-timing contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical terminology related to engineering and circuit design in the context of serial data transmission.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udas
    -0.07
    Thu
    -0.07
    _third
    -0.07
    _Level
    -0.07
    _o
    -0.06
     intent
    -0.06
     نیم
    -0.06
    átku
    -0.06
    (lp
    -0.06
    ็บไซต
    -0.06
    POSITIVE LOGITS
    Mount
    0.07
     rolls
    0.07
     пят
    0.06
    rapy
    0.06
    Roll
    0.06
    ，它
    0.06
     concerned
    0.06
    [MAX
    0.06
    ="--
    0.06
     advancing
    0.06
    Activations Density 0.019%

    No Known Activations